Skip to content

可以实现不同数据使用不同的loss_scale吗 #4139

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
zsxm1998 opened this issue May 8, 2025 · 0 comments
Open

可以实现不同数据使用不同的loss_scale吗 #4139

zsxm1998 opened this issue May 8, 2025 · 0 comments

Comments

@zsxm1998
Copy link
Contributor

zsxm1998 commented May 8, 2025

Describe the feature
比如有的对话数据所有的assistant回复都比较重要,而有其他的对话,只想训练最后一轮的assistant回复(例如前面的回复有错误,在最后一轮修正)。能否开发一个特性,通过在数据集中给某些数据设置独属的loss_scale,其他未设置的使用默认值。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant